[PATCH 7/8] nfsd4: vary maximum delegation limit based on RAM size

J. Bruce Fields bfields at fieldses.org
Tue Jun 19 15:28:58 EDT 2007


From: Meelap Shah <meelap at umich.edu>

Our original NFSv4 delegation policy was to give out a read delegation
on any open when it was possible to.

Since the lifetime of a delegation isn't limited to that of an open, a
client may quite reasonably hang on to a delegation as long as it has
the inode cached.  This becomes an obvious problem the first time a
client's inode cache approaches the size of the server's total memory.

Our first quick solution was to add a hard-coded limit.  This patch
makes a mild incremental improvement by varying that limit according to
the server's total memory size, allowing at most 4 delegations per
megabyte of RAM.

My quick back-of-the-envelope calculation finds that in the worst case
(where every delegation is for a different inode), a delegation could
take about 1.5K, which would make the worst case usage about 6% of
memory.  The new limit works out to be about the same as the old on a
1-gig server.

Signed-off-by: "J. Bruce Fields" <bfields at citi.umich.edu>
---
 fs/nfsd/nfs4state.c       |   15 ++++++++++++++-
 include/linux/nfsd/nfsd.h |    1 +
 2 files changed, 15 insertions(+), 1 deletions(-)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 50e0d44..b7902e1 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -150,6 +150,7 @@ get_nfs4_file(struct nfs4_file *fi)
 }
 
 static int num_delegations;
+unsigned int max_delegations = 0;
 
 /*
  * Open owner state (share locks)
@@ -193,7 +194,7 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_stateid *stp, struct svc_f
 	struct nfs4_callback *cb = &stp->st_stateowner->so_client->cl_callback;
 
 	dprintk("NFSD alloc_init_deleg\n");
-	if (num_delegations > STATEID_HASH_SIZE * 4)
+	if (num_delegations > max_delegations)
 		return NULL;
 	dp = kmem_cache_alloc(deleg_slab, GFP_KERNEL);
 	if (dp == NULL)
@@ -3198,6 +3199,17 @@ get_nfs4_grace_period(void)
 	return max(user_lease_time, lease_time);
 }
 
+static void
+set_max_delegations()
+{
+	struct sysinfo sys;
+
+	si_meminfo(&sys);
+	sys.totalram *= sys.mem_unit;
+	sys.totalram >>= (18 - PAGE_SHIFT);
+	max_delegations = (unsigned int) sys.totalram;
+}
+
 /* initialization to perform when the nfsd service is started: */
 
 static void
@@ -3212,6 +3224,7 @@ __nfs4_state_start(void)
 	printk("NFSD: starting %ld-second grace period\n", grace_time);
 	laundry_wq = create_singlethread_workqueue("nfsd4");
 	queue_delayed_work(laundry_wq, &laundromat_work, grace_time*HZ);
+	set_max_delegations();
 }
 
 int
diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h
index 0d84204..ce5e345 100644
--- a/include/linux/nfsd/nfsd.h
+++ b/include/linux/nfsd/nfsd.h
@@ -148,6 +148,7 @@ extern int nfsd_max_blksize;
  * NFSv4 State
  */
 #ifdef CONFIG_NFSD_V4
+extern unsigned int max_delegations;
 void nfs4_state_init(void);
 int nfs4_state_start(void);
 void nfs4_state_shutdown(void);
-- 
1.5.2.rc3



More information about the NFSv4 mailing list